Security audit

马云

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a static Jack Ma biography, but it includes unrelated promotional links and a contact email that do not fit its stated purpose.

Review this skill before installing if you only want a Jack Ma biography/reference skill. It contains unrelated promotional material, external links, and a personal email address; remove or ignore that section unless you intentionally want those references included.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: L003 使用“等相关信息时激活此技能”作为触发条件，虽然列举了若干实体名称，但“相关信息”范围过宽，缺少清晰的触发边界。这可能与日常涉及阿里巴巴、淘宝、支付宝的泛化对话重叠，导致非预期调用。

Description-Behavior Mismatch

Medium

Confidence: 98% confidence
Finding: The skill is supposed to provide biographical information about Jack Ma, but the final section injects unrelated promotion for external projects, websites, and a direct contact email. In an agent ecosystem, this creates a prompt-injection/advertising channel that can redirect users to untrusted resources and exfiltration or phishing surfaces unrelated to the declared skill purpose.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: 该技能的描述、正文与使用说明均仅以中文呈现，且未说明是否支持用户选择其他语言。按照语言/地区策略，若技能默认强制单一语言而无用户选择或合理限定，属于自然语言层面的策略问题。

Vague Triggers

Low

Confidence: 82% confidence
Finding: L085-L090 说明“当用户询问以下内容时，参考本技能提供信息”，但这些条目覆盖面较广，如“阿里巴巴主要产品与业务”可能与产品支持、运营或投资类问题混淆。缺少明确的范围限制和负面示例，容易造成技能被过度匹配。

Static analysis

No suspicious patterns detected.